toggle visibility Search & Display Options

Select All    Deselect All
 |   | 
Details
   print
  Records Links
Author Axel Barroso-Laguna; Edgar Riba; Daniel Ponsa; Krystian Mikolajczyk edit   pdf
url  doi
openurl 
  Title Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 5835-5843  
  Keywords  
  Abstract We introduce a novel approach for keypoint detection task that combines handcrafted and learned CNN filters within a shallow multi-scale architecture. Handcrafted filters provide anchor structures for learned filters, which localize, score and rank repeatable features. Scale-space representation is used within the network to extract keypoints at different levels. We design a loss function to detect robust features that exist across a range of scales and to maximize the repeatability score. Our Key.Net model is trained on data synthetically created from ImageNet and evaluated on HPatches benchmark. Results show that our approach outperforms state-of-the-art detectors in terms of repeatability, matching performance and complexity.  
  Address Seul; Corea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes MSIAU; 600.122 Approved no  
  Call Number Admin @ si @ BRP2019 Serial 3290  
Permanent link to this record
 

 
Author Hamed H. Aghdam; Abel Gonzalez-Garcia; Joost Van de Weijer; Antonio Lopez edit   pdf
url  doi
openurl 
  Title Active Learning for Deep Detection Neural Networks Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 3672-3680  
  Keywords  
  Abstract The cost of drawing object bounding boxes (ie labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection.  
  Address Seul; Korea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; LAMP; 600.124; 600.109; 600.141; 600.120; 600.118 Approved no  
  Call Number Admin @ si @ AGW2019 Serial 3321  
Permanent link to this record
 

 
Author Felipe Codevilla; Eder Santana; Antonio Lopez; Adrien Gaidon edit   pdf
url  doi
openurl 
  Title Exploring the Limitations of Behavior Cloning for Autonomous Driving Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 9328-9337  
  Keywords  
  Abstract Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor policies end-to-end, but scaling to the full spectrum of driving behaviors remains an unsolved problem. In this paper, we propose a new benchmark to experimentally investigate the scalability and limitations of behavior cloning. We show that behavior cloning leads to state-of-the-art results, executing complex lateral and longitudinal maneuvers, even in unseen environments, without being explicitly programmed to do so. However, we confirm some limitations of the behavior cloning approach: some well-known limitations (eg, dataset bias and overfitting), new generalization issues (eg, dynamic objects and the lack of a causal modeling), and training instabilities, all requiring further research before behavior cloning can graduate to real-world driving. The code, dataset, benchmark, and agent studied in this paper can be found at github.  
  Address Seul; Korea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes ADAS; 600.124; 600.118 Approved no  
  Call Number Admin @ si @ CSL2019 Serial 3322  
Permanent link to this record
 

 
Author David Berga; Xose R. Fernandez-Vidal; Xavier Otazu; Xose M. Pardo edit   pdf
url  doi
openurl 
  Title SID4VAM: A Benchmark Dataset with Synthetic Images for Visual Attention Modeling Type Conference Article
  Year 2019 Publication (up) 18th IEEE International Conference on Computer Vision Abbreviated Journal  
  Volume Issue Pages 8788-8797  
  Keywords  
  Abstract A benchmark of saliency models performance with a synthetic image dataset is provided. Model performance is evaluated through saliency metrics as well as the influence of model inspiration and consistency with human psychophysics. SID4VAM is composed of 230 synthetic images, with known salient regions. Images were generated with 15 distinct types of low-level features (e.g. orientation, brightness, color, size...) with a target-distractor popout type of synthetic patterns. We have used Free-Viewing and Visual Search task instructions and 7 feature contrasts for each feature category. Our study reveals that state-ofthe-art Deep Learning saliency models do not perform well with synthetic pattern images, instead, models with Spectral/Fourier inspiration outperform others in saliency metrics and are more consistent with human psychophysical experimentation. This study proposes a new way to evaluate saliency models in the forthcoming literature, accounting for synthetic images with uniquely low-level feature contexts, distinct from previous eye tracking image datasets.  
  Address Seul; Corea; October 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICCV  
  Notes NEUROBIT; 600.128 Approved no  
  Call Number Admin @ si @ BFO2019b Serial 3372  
Permanent link to this record
 

 
Author Mohammad Rouhani; Angel Sappa edit  openurl
  Title Implicit B-Spline Fitting Using the 3L Algorithm Type Conference Article
  Year 2011 Publication (up) 18th IEEE International Conference on Image Processing Abbreviated Journal  
  Volume Issue Pages 893-896  
  Keywords  
  Abstract  
  Address Brussels, Belgium  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference ICIP  
  Notes ADAS Approved no  
  Call Number Admin @ si @ RoS2011a; ADAS @ adas @ Serial 1782  
Permanent link to this record
 

 
Author Eduardo Aguilar; Petia Radeva edit  url
openurl 
  Title Class-Conditional Data Augmentation Applied to Image Classification Type Conference Article
  Year 2019 Publication (up) 18th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 11679 Issue Pages 182-192  
  Keywords CNNs; Data augmentation; Deep learning; Epistemic uncertainty; Image classification; Food recognition  
  Abstract Image classification is widely researched in the literature, where models based on Convolutional Neural Networks (CNNs) have provided better results. When data is not enough, CNN models tend to be overfitted. To deal with this, often, traditional techniques of data augmentation are applied, such as: affine transformations, adjusting the color balance, among others. However, we argue that some techniques of data augmentation may be more appropriate for some of the classes. In order to select the techniques that work best for particular class, we propose to explore the epistemic uncertainty for the samples within each class. From our experiments, we can observe that when the data augmentation is applied class-conditionally, we improve the results in terms of accuracy and also reduce the overall epistemic uncertainty. To summarize, in this paper we propose a class-conditional data augmentation procedure that allows us to obtain better results and improve robustness of the classification in the face of model uncertainty.  
  Address Salermo; Italy; September 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CAIP  
  Notes MILAB; no proj Approved no  
  Call Number Admin @ si @ AgR2019 Serial 3366  
Permanent link to this record
 

 
Author Estefania Talavera; Nicolai Petkov; Petia Radeva edit   pdf
url  doi
openurl 
  Title Unsupervised Routine Discovery in Egocentric Photo-Streams Type Conference Article
  Year 2019 Publication (up) 18th International Conference on Computer Analysis of Images and Patterns Abbreviated Journal  
  Volume 11678 Issue Pages 576-588  
  Keywords Routine discovery; Lifestyle; Egocentric vision; Behaviour analysis  
  Abstract The routine of a person is defined by the occurrence of activities throughout different days, and can directly affect the person’s health. In this work, we address the recognition of routine related days. To do so, we rely on egocentric images, which are recorded by a wearable camera and allow to monitor the life of the user from a first-person view perspective. We propose an unsupervised model that identifies routine related days, following an outlier detection approach. We test the proposed framework over a total of 72 days in the form of photo-streams covering around 2 weeks of the life of 5 different camera wearers. Our model achieves an average of 76% Accuracy and 68% Weighted F-Score for all the users. Thus, we show that our framework is able to recognise routine related days and opens the door to the understanding of the behaviour of people.  
  Address Salermo; Italy; September 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title LNCS  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference CAIP  
  Notes MILAB; no proj Approved no  
  Call Number Admin @ si @ TPR2019a Serial 3367  
Permanent link to this record
 

 
Author Fernando Vilariño; Panagiota Spyridonos; Jordi Vitria; Fernando Azpiroz; Petia Radeva edit   pdf
doi  isbn
openurl 
  Title Automatic Detection of Intestinal Juices in Wireless Capsule Video Endoscopy Type Conference Article
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition Abbreviated Journal  
  Volume 4 Issue Pages 719-722  
  Keywords Clinical diagnosis , Endoscopes , Fluids and secretions , Gabor filters , Hospitals , Image sequence analysis , Intestines , Lighting , Shape , Visualization  
  Abstract Wireless capsule video endoscopy is a novel and challenging clinical technique, whose major reported drawback relates to the high amount of time needed for video visualization. In this paper, we propose a method for the rejection of the parts of the video resulting not valid for analysis by means of automatic detection of intestinal juices. We applied Gabor filters for the characterization of the bubble-like shape of intestinal juices in fasting patients. Our method achieves a significant reduction in visualization time, with no relevant loss of valid frames. The proposed approach is easily extensible to other image analysis scenarios where the described pattern of bubbles can be found.  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN 1051-4651 ISBN 0-7695-2521-0 Medium  
  Area 800 Expedition Conference ICPR  
  Notes MV;OR;MILAB;SIAI Approved no  
  Call Number BCNPCL @ bcnpcl @ VSV2006b; IAM @ iam @ VSV2006g Serial 727  
Permanent link to this record
 

 
Author Joan Mas; B. Lamiroy; Gemma Sanchez; Josep Llados edit  openurl
  Title Automatic Adjacency Grammar Generation from User Drawn Sketches Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition (ICPR´06), 2: 1026–1029 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number DAG @ dag @ MLS2006a Serial 709  
Permanent link to this record
 

 
Author Oriol Ramos Terrades; Salvatore Tabbone; Ernest Valveny edit  openurl
  Title Combination of shape descriptors using an adaptation of boosting Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition (ICPR´06), 2: 764–767 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes DAG Approved no  
  Call Number DAG @ dag @ RTV2006 Serial 718  
Permanent link to this record
 

 
Author Sergio Escalera; Oriol Pujol; Petia Radeva edit  openurl
  Title ECOC-ONE: A novel coding and decoding strategy Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition (ICPR´06), 3: 578–581, ISBN: 0–7695–2521–0 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes MILAB;HuPBA Approved no  
  Call Number BCNPCL @ bcnpcl @ EPR2006b Serial 693  
Permanent link to this record
 

 
Author Sergio Escalera; Oriol Pujol; Petia Radeva edit  openurl
  Title Boosted Landmarks of Contextual Descriptors and Forest-ECOC: a novel framework to detect and classify objects in cluttered scenes Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition (ICPR´06), 4: 104–107, ISBN: 0–7695–2521–0 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes MILAB;HuPBA Approved no  
  Call Number BCNPCL @ bcnpcl @ EPR2006a Serial 692  
Permanent link to this record
 

 
Author Fadi Dornaika; Franck Davoine edit  openurl
  Title Facial expression recognition using auto-regressive models Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition (ICPR´06), ISBN: 0–7695–2521–0, 4: 520–523 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number Admin @ si @ DoD2006a Serial 734  
Permanent link to this record
 

 
Author Michael Villamizar; A. Sanfeliu; Juan Andrade edit  openurl
  Title Computation of Rotation Local Invariant Features using the Integral Image for Real Time Object Detection Type Miscellaneous
  Year 2006 Publication (up) 18th International Conference on Pattern Recognition, 81–85 Abbreviated Journal  
  Volume Issue Pages  
  Keywords  
  Abstract  
  Address Hong Kong  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference  
  Notes Approved no  
  Call Number Admin @ si @ VSA2006a Serial 663  
Permanent link to this record
 

 
Author Angel Morera; Angel Sanchez; Angel Sappa; Jose F. Velez edit   pdf
url  openurl
  Title Robust Detection of Outdoor Urban Advertising Panels in Static Images Type Conference Article
  Year 2019 Publication (up) 18th International Conference on Practical Applications of Agents and Multi-Agent Systems Abbreviated Journal  
  Volume Issue Pages 246-256  
  Keywords Object detection; Urban ads panels; Deep learning; Single Shot Detector (SSD) architecture; Intersection over Union (IoU) metric; Augmented Reality  
  Abstract One interesting publicity application for Smart City environments is recognizing brand information contained in urban advertising panels. For such a purpose, a previous stage is to accurately detect and locate the position of these panels in images. This work presents an effective solution to this problem using a Single Shot Detector (SSD) based on a deep neural network architecture that minimizes the number of false detections under multiple variable conditions regarding the panels and the scene. Achieved experimental results using the Intersection over Union (IoU) accuracy metric make this proposal applicable in real complex urban images.  
  Address Aquila; Italia; June 2019  
  Corporate Author Thesis  
  Publisher Place of Publication Editor  
  Language Summary Language Original Title  
  Series Editor Series Title Abbreviated Series Title  
  Series Volume Series Issue Edition  
  ISSN ISBN Medium  
  Area Expedition Conference PAAMS  
  Notes MSIAU; 600.130; 600.122 Approved no  
  Call Number Admin @ si @ MSS2019 Serial 3270  
Permanent link to this record
Select All    Deselect All
 |   | 
Details
   print

Save Citations:
Export Records: